Power Usage And Battery Life
Given AMD’s improved power efficiency claims, we’re naturally interested in Llano’s alacrity here. After all, AMD’s presence in the mobile space is modest. So it’ll take demonstrations of solid battery life to complement respectable performance if the company hopes to make inroads with mobile vendors perpetually pushing smaller form-factors and more run-time.
Our first test is the Tom’s Hardware Real Life Usage (RLU) benchmark, something our own Andrew Ku created. This test simulates actual use by Web browsing, performing Microsoft office tasks, and viewing a DivX movie.
Because we’re benchmarking two laptops with different batteries and screens, we’ve removed those variables by simply measuring power use when outputting to an external monitor.
Based on the chart, you’d expect that the A8-3500M APU would have the advantage over Intel’s Core i5-2520M in general power usage.
But Intel’s processor dips into a low power state more often. This mode-switching results in very similar power numbers. The Core i5-2520M averaged 12.8 watts during Web browsing, 17 watts during office tasks, and 19.4 watts in movie playback. In contrast, the A8-3500M averages 15.2 watts, 16.3 watts, and 19.5 watts, respectively. And while the Core i5 demonstrates faster CPU performance in our benchmarks, that isn’t as much of a factor when you’re surfing the net, typing a document, or playing back a movie. The experience is the same.
Now let’s see how these platforms handle a graphics load:
The power use in the above graph is a result of a controlled test on an external monitor, so we repeated this metric again, this time using the laptop’s own display. The A8-3500M laptop lasted two hours and 12 minutes. Assuming the Intel laptop used the exact same battery, it would run for one hour and 22 minutes.
This is very impressive. Not only does the A8-3500M get about twice as much time out of its battery, it does so while delivering far better graphics performance. The implications of this are profound: a Llano laptop user might be able to play a mainstream 3D game for an entire two-hour flight with decent frame rates, while the Intel Core i5-based platform would only last for half of the flight with choppy performance. There does, in fact, seem to be validity in AMD’s excitement over its improved power story, and of course this is a real advantage when it comes to mobile devices.
Finally, we wanted to look into the company’s claims about AMD AllDay power. Now, AMD defines “All Day” battery life as 8+ hours in Windows, idling. This is ridiculous, plain and simple. Nobody powers on their system and lets it sit there just to claim it was on from nine to five at work. AMD needs to sit down and let the engineers do their thing. The real-world power figures tell a compelling-enough tale without some marketing-driven buzzword.
On our A8-3500M-based test mule, we did try to see how long the battery would last using the lowest monitor brightness and a very simple workload: document reading. We used the Battery Eater Pro benchmark to simulate someone browsing through a document and the machine lasted 7 hours and 40 minutes. That’s quite a feat for a full-sized laptop running an AMD processor, given the company's track record in the mobile space. The Sabine platform brings the fight to Intel's turf.